Video Transcription & Indexing Pipeline
Automatically transcribe video content with speaker identification, timestamps, and full-text indexing for downstream search and analytics.
from mixpeek import Mixpeekclient = Mixpeek(api_key="YOUR_API_KEY")namespace = client.namespaces.create(name="transcripts")collection = client.collections.create(namespace_id=namespace.id,name="meetings",extractors=["audio-transcription", "speaker-diarization"])# Upload videos - transcription happens automaticallyclient.buckets.upload(collection_id=collection.id,url="s3://your-bucket/meeting-recordings/")# Retrieve transcriptdocs = client.documents.search(namespace_id=namespace.id,collection_ids=[collection.id],query="action items from last week")
Feature Extractors
Audio Transcription
Transcribe audio content to text
Speaker Diarization
Identify and separate different speakers in audio content
Retriever Stages
Related Recipes & Resources
Explore these related resources to deepen your understanding and discover more powerful features
Audio Transcription
Transcribe audio content to text
Speaker Diarization
Identify and separate different speakers in audio content
Speaker Diarization
Identifying who spoke when in audio recordings
Video Content Analytics Pipeline
Analyze video content at scale to extract insights: scene composition, speaker time, topic distribution, and sentiment across your video library.
Video RAG Pipeline
Retrieval-augmented generation specifically designed for video content. Decomposes videos into scenes and transcripts, retrieves relevant segments for a given question, and passes them as context to an LLM with precise timestamp citations.
Searchable Video Library
Turn an unstructured video archive into a fully searchable library. Each video is decomposed into scenes with transcriptions, visual embeddings, and metadata. Users search by natural language and jump directly to the relevant moment in any video.